Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Safety performance of the Waymo rider-only automated driving system [pdf]

storage.googleapis.com

Post reply on HN
Print view View original

41–50 of 58 posts

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#41

Post by pclmulqdq »

dzdt wrote: post #24
ghaff wrote: post #22

Earlier quoted context omitted.

>I have a feeling human drivers do to some degree. Sure. In general, people will try not to hit the brakes any harder than they have to especially if they have the situational awareness to know someone is close (maybe too close) behind them.

More often in my experience they will randomly tap the brakes to try to get the person behind them to back off: "brake check".

If you tend to drive too close behind people, you will see this happen a lot - people really don't like getting involved in highway pile-ups, so it's better to give you a brake check than to wait until it actually matters. However, it is very rare for people to "brake check" you unless you do that.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#42

Post by nradov »

gerad wrote: post #33
pb7 wrote: post #25

Earlier quoted context omitted.

SF is not an easy locale to test in. Sure, there is no snow, but the city is narrow, dense, with a lot of challenging situations including fog, rain, and crackheads. This success seems promising.

SF is a terrible city to drive in. Narrow streets, terrible hills, a huge diversity of traffic: pedestrians, cyclists, electric scooters, buses, light rail, trains. Highly congested. Plenty of tourists driving (it’s not like NY or London where people who are visiting know not to drive).

SF doesn't seem that bad? At least not compared to Boston in the winter.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#43

Post by antisthenes »

dzdt wrote: post #24
ghaff wrote: post #22

Earlier quoted context omitted.

>I have a feeling human drivers do to some degree. Sure. In general, people will try not to hit the brakes any harder than they have to especially if they have the situational awareness to know someone is close (maybe too close) behind them.

More often in my experience they will randomly tap the brakes to try to get the person behind them to back off: "brake check".

This only happens when someone is following at speed and does not maintain the proper distance.

Brake checking at yield signs and stop signs isn't really a thing.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#44

Post by sbaiddn »

dzdt wrote: post #24
ghaff wrote: post #22

Earlier quoted context omitted.

>I have a feeling human drivers do to some degree. Sure. In general, people will try not to hit the brakes any harder than they have to especially if they have the situational awareness to know someone is close (maybe too close) behind them.

More often in my experience they will randomly tap the brakes to try to get the person behind them to back off: "brake check".

You're tailgating

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#46

Post by nawgz »

jeffbee wrote: post #15
nawgz wrote: post #5

Earlier quoted context omitted.

"Hey guys, self-driving is a decent sprint but I think you should expand the scope to include detecting and modeling driver behavior in nearby vehicles. Add a quick study for HCI to warn drivers of their dangerous aberrant behavior and I think we might have something real here!" - tropsis, 2023

Predicting the behavior of other actors on the road is a core feature of Waymo. https://waymo.com/research/identifying-driver-interactions-v...

Of course.

It's doing that by looking at the vehicle as the agent though; it has nothing to do with "the body language of this pilot suggests this vehicle will do X", it's just a predictive module because it's useless to be able to see another car if you can't predict it's going to go X units forward in the next time tick(s).

Adding a layer that models human drivers to augment the prediction of this module you link would be a waste of time.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#47

Post by Fatnino »

nradov wrote: post #42
gerad wrote: post #33

Earlier quoted context omitted.

SF is a terrible city to drive in. Narrow streets, terrible hills, a huge diversity of traffic: pedestrians, cyclists, electric scooters, buses, light rail, trains. Highly congested. Plenty of tourists driving (it’s not like NY or London where people who are visiting know not to drive).

SF doesn't seem that bad? At least not compared to Boston in the winter.

The grid in Boston is a joke.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#48

Post by minwcnt5 »

parton wrote: post #16

Silly question: will the Waymo AV use the horn? I see a few parking lot incidents where another driver backed into the front of a stationary Waymo AV at ~2 mph. I think a human driver might have tried honking at the other driver, on seeing a slow-motion collision about to occur.

It does use the horn, but it's not clear whether it can/did in these incidents.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#49

Post by tialaramex »

trompetenaccoun wrote: post #34
alphabetting wrote: post #14

Earlier quoted context omitted.

I don't think there is hard data. From two rides experience in Arizona it feels eerily similar to a human driver minus it adhering the speed limit.

And minus the times when it gets stuck and needs to be rescued by human driver either remotely or an actual Waymo guy coming over and getting in the car. Doesn't happen every time of course but it does happen.

Remote humans can't drive Waymo's vehicles. They can reach into the car's model of the world to correct something it misunderstood (e.g. car is confused by misplaced cone and thinks the entire carriageway is closed, actually only the left lane is closed) but they can't control the vehicle remotely at all. It's extraordinary to me how many HN readers seem to think that somehow remotely driving cars would be a good idea, but then I remember how many incredibly dumb start-up ideas get funded and it's less surprising.

Re: Safety performance of the Waymo rider-only automated driving system [pdf]

#50

Post by gregshap »

hardtke wrote: post #37
ra7 wrote: post #8

If you don't want to read the full 30 page paper, Waymo has a blog post summarizing it: https://blog.waymo.com/2023/02/first-million-rider-only-mile... It's refreshing to see Waymo continue to be transparent about their safety data. I guess it's easier to do when you have a stellar safety record.

I've probably driven half a million miles and I don't remember having 10 incidents (I probably have, just don't remember). So I'd conclude I'm at least as safe a driver as Waymo. Even if not true, most people are going to feel that way when they see the data. Human nature.

Probably more highway miles though to reach that number. City accidents I expect would be lower severity but higher frequency.
Post reply on HN